Safety & alignment

We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level, CRAFT aligns large reasoning models to generate safety-aware reasoning traces by explicitly optimizing objectives defined over the hidden state space. Methodologically, CRAFT integrates contrastive representation learning with reinforcement learning to separate

Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed human behavior. We compare 120 base-aligned model pairs on more than 10,000 real human decisions in multi-round strategic games - bargaining, persuasion, negotiation, and repeated matrix games. In these settings, base models outperform their aligned counterparts in predicting human choices by nearly 10:1, robustly across model families, prompt formulation

Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? We present the first systematic study of this question, applying DPO to Janus-Pro at 1B and 7B parameters under seven training strategies and two post-hoc methods. The central finding is negative: generation quality resists DPO alignment across all tested conditions on this architecture. No method improves generation CLIPScore at 7B (|Delta| 0.5

Culture shapes reasoning, values, prioritization, and strategic decision-making, yet large language models (LLMs) often exhibit cultural biases that misalign with target populations. As LLMs are increasingly used for strategic decision-making, policy support, and document engineering tasks such as summarization, categorization, and compliance-oriented auditing, improving cultural alignment is important for ensuring that downstream analyses and recommendations reflect target-population value prof

To meet the demands of increasingly diverse dexterous hand hardware, it is crucial to develop a policy that enables zero-shot cross-embodiment grasping without redundant re-learning. Cross-embodiment alignment is challenging due to heterogeneous hand kinematics and physical constraints. Existing approaches typically predict intermediate motion targets and retarget them to each embodiment, which may introduce errors and violate embodiment-specific limits, hindering transfer across diverse hands.

Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic supervision and are not explicitly designed to capture high-level visual structure. Recent representation-alignment methods (e.g., REPA) suggest that pretrained visual features can substantially improve diffusion training, and visual co-denoising has emerged as a

We study a simple unsupervised regularization scheme for autoencoders called Manifold-Matching (MMAE): we align the pairwise distances in the latent space to those of the input data space by minimizing mean squared error. Because alignment occurs on pairwise distances rather than coordinates, it can also be extended to a lower-dimensional representation of the data, adding flexibility to the method. We find that this regularization outperforms similar methods on metrics based on preservation of

Recent empirical results have demonstrated that training large language models (LLMs) with negative-only feedback can match or exceed standard reinforcement learning from human feedback (RLHF). Negative Sample Reinforcement achieves parity with PPO on mathematical reasoning; Distributional Dispreference Optimization trains effectively using only dispreferred samples; and Constitutional AI outperforms pure RLHF on harmlessness benchmarks. Yet no unified theoretical account explains why negative s

Creative plot generation presents a fundamental challenge for language models: transforming a concise premise into a coherent narrative that sustains global structure, character development, and emotional resonance. Although recent Large Language Models (LLMs) demonstrate strong fluency across general-purpose tasks, they typically require preference alignment to perform well on specialized domains such as creative plot generation. However, conducting such alignment at the scale of frontier LLMs

Chronological age predictors often fail to achieve out-of-distribution (OOD) gen- eralization due to exogenous attributes such as race, gender, or tissue. Learning an invariant representation with respect to those attributes is therefore essential to improve OOD generalization and prevent overly optimistic results. In predic- tive settings, these attributes motivate bias mitigation; in causal analyses, they appear as confounders; and when protected, their suppression leads to fairness. We cohere

In this paper, we investigate the potential of open-source Large Language Models (LLMs) for grading Unified Modeling Language (UML) class diagrams. In contrast to existing work, which primarily evaluates proprietary LLMs, we focus on non-proprietary models, making our approach suitable for universities where transparency and cost are critical. Additionally, existing studies assess performance over complete diagrams rather than individual criteria, offering limited insight into how automated grad

Theory of Mind (ToM) refers to the ability to reason about others' mental states, and higher-order ToM involves considering that others also possess their own ToM. Equipping large language model (LLM)-driven agents with ToM has long been considered to improve their coordination in multiagent collaborative tasks. However, we find that misaligned ToM orders-mismatches in the depth of ToM reasoning between agents-can lead to insufficient or excessive reasoning about others, thereby impairing their

Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, real-world deployments often require context-dependent safety rules that vary across users, regions, and applications. Existing approaches struggle to provide such conditional control: parameter-level alignment entangles safety behaviors with general capabilities, while prompt-based methods rely on natural language instructions that provide weak enforcement. W

In near-field extremely large-scale multiple-input multiple-output (XL-MIMO) systems, spherical wavefront propagation expands the traditional beam codebook into the joint angular-distance domain, rendering conventional beam training prohibitively inefficient, especially in complex 3-dimensional (3D) low-altitude environments. Furthermore, since near-field beam variations are deeply coupled not only with user positions but also with the physical surroundings, precise beam alignment demands profou

Multi-agent orchestration -- in which a hidden coordinator manages specialized worker agents -- is becoming the default architecture for enterprise AI deployment, yet the safety implications of orchestrator invisibility have never been empirically tested. We conducted a preregistered 3x2 experiment (365 runs, 5 agents per run) crossing three organizational structures (visible leader, invisible orchestrator, flat) with two alignment conditions (base, heavy), using Claude Sonnet 4.5. Four confirma

Safety alignment in diffusion language models (dLLMs) relies on a single load-bearing assumption: that committed tokens are permanent. We show that violating this assumption, by re-masking committed refusal tokens and injecting a short affirmative prefix, achieves 74-82% ASR on HarmBench across all three publicly available safety-tuned dLLMs, rising to 92-98% with a generic 8-token compliance prefix. We call this attack TrajHijack; it is the first trajectory-level attack on dLLMs, requires no gr

Large language models (LLMs) have made remarkable progress in generating fluent text, but they still face a critical challenge of contextual misalignment in long-term and dynamic dialogue. When human users omit premises, simplify references, or shift context abruptly during interactions with LLMs, the models may fail to capture their actual intentions, producing mechanical or off-topic responses that weaken the collaborative potential of dialogue. To address this problem, this paper proposes a c

Large Language Models (LLMs) have demonstrated exceptional logical reasoning capabilities but frequently struggle with the continuous spatiotemporal dynamics governed by Partial Differential Equations (PDEs), often resulting in non-physical hallucinations. Existing approaches typically resort to costly, domain-specific fine-tuning, which severely limits cross-domain generalization and interpretability. To bridge this gap, we propose OMNIFLOW, a neuro-symbolic architecture designed to ground froz

Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving LLMs vulnerable to long-tail risks. More crucially, we posit that LLMs possess an inherent state of moral indifference due to compressing distinct moral concepts into uniform probability distributions. We verify and remedy this indifference in LLMs' latent representations, utilizing 251k moral vectors constructed upon P

As Large Language Models (LLMs) become more powerful and autonomous, they increasingly face conflicts and dilemmas in many scenarios. We first summarize and taxonomize these diverse conflicts. Then, we model the LLM's preferences to make different choices as a priority graph, where instructions and values are nodes, and the edges represent context-specific priorities determined by the model's output distribution. This graph reveals that a unified stable LLM alignment is very challenging, because

Existing time series forecasting methods primarily rely on the numerical data itself. However, real-world time series exhibit complex patterns associated with multimodal information, making them difficult to predict with numerical data alone. While several multimodal time series forecasting methods have emerged, they either utilize text with limited supplementary information or focus merely on representation extraction, extracting minimal textual information for forecasting. To unlock the Value

While current emotional support dialogue systems typically rely on expert-defined scalar rewards for alignment, these signals suffer from severe information sparsity. They cannot explain why a response failed or how to adapt to dynamic user states, often diverging from the actual goal of facilitating positive emotional shifts. In practice, the most direct and reliable learning signal emerges from the user's continuous reactions during ongoing interaction. We therefore propose Reaction Aware Poli

Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to jailbreak attacks that undermine their safety alignment. Existing defense mechanisms typically rely on post hoc filtering applied only to the final output, leaving intermediate reasoning steps unmonitored and vulnerable to adversarial manipulation. To address this gap, this paper proposes a SaFer Chain-of-Thought (SFCoT) framework, which proactively evalua

Morphology-control co-design concerns the coupled optimization of an agent's body structure and control policy. This problem exhibits a bi-level structure, where the control dynamically adapts to the morphology to maximize performance. Existing methods typically neglect the control's adaptation dynamics by adopting a single-level formulation that treats the control policy as fixed when optimizing morphology. This can lead to inefficient optimization, as morphology updates may be misaligned with

Industrial financial systems operate on temporal event sequences such as transactions, user actions, and system logs. While recent research emphasizes representation learning and large language models, production systems continue to rely heavily on handcrafted statistical features due to their interpretability, robustness under limited supervision, and strict latency constraints. This creates a persistent disconnect between learned embeddings and feature-based pipelines. We introduce Embedding-A

The safety and reliability of vision-language models (VLMs) are a crucial part of deploying trustworthy agentic AI systems. However, VLMs remain vulnerable to jailbreaking attacks that undermine their safety alignment to yield harmful outputs. In this work, we extend the Randomized Embedding Smoothing and Token Aggregation (RESTA) defense to VLMs and evaluate its performance against the JailBreakV-28K benchmark of multi-modal jailbreaking attacks. We find that RESTA is effective in reducing atta

Deploying autonomous driving systems requires robustness against long-tail scenarios that are rare but safety-critical. While adversarial training offers a promising solution, existing methods typically decouple scenario generation from policy optimization and rely on heuristic surrogates. This leads to objective misalignment and fails to capture the shifting failure modes of evolving policies. This paper presents ADV-0, a closed-loop min-max optimization framework that treats the interaction be

As LLMs are globally deployed, aligning their cultural value orientations is critical for safety and user engagement. However, existing benchmarks face the Construct-Composition-Context ($C^3$) challenge: relying on discriminative, multiple-choice formats that probe value knowledge rather than true orientations, overlook subcultural heterogeneity, and mismatch with real-world open-ended generation. We introduce DOVE, a distributional evaluation framework that directly compares human-written text

Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, harming overall performance due to the "needle-in-the-haystack" problem. To address these challenges, we propose a multi-stage alignment met

Humans learn from catastrophic mistakes not through numerical penalties, but through qualitative suffering that reshapes who they are. Current AI safety approaches replicate none of this. Reward shaping captures magnitude, not meaning. Rule-based alignment constrains behaviour, but does not change it. We propose Emotional Cost Functions, a framework in which agents develop Qualitative Suffering States, rich narrative representations of irreversible consequences that persist forward and actively

Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at inference time. However, we observe that these approaches are usually restricted to differentiable or cheap reward models, the formulation of the underlying pretrained generative model, or are memory/compute inefficient. We instead propose a simple trust-region based search algorithm (TRS) which treats the pre-trained generative and reward models as a black-box

Tensions between AI Safety (AIS) and AI Ethics (AIE) have increasingly surfaced in AI governance and public debates about AI, leading to what we term the "responsible AI divides". We introduce a model that categorizes four modes of engagement with the tensions: radical confrontation, disengagement, compartmentalized coexistence, and critical bridging. We then investigate how critical bridging, with a particular focus on bridging problems, offers one of the most viable constructive paths for adva

Large language models appear to develop internal representations of emotion -- "emotion circuits," "emotion neurons," and structured emotional manifolds have been reported across multiple model families. But every study making these claims uses stimuli signalled by explicit emotion keywords, leaving a fundamental question unanswered: do these circuits detect genuine emotional meaning, or do they detect the word "devastated"? We present the first clinical validity test of emotion circuit claims u

As AI systems advance in capabilities, measuring their safety and alignment to human values is becoming paramount. A fast-growing field of AI research is devoted to developing such assessments. However, most current advances therein may be ill-suited for assessing AI systems across real-world deployments. Standard methods prompt large language models (LLMs) in a questionnaire-style to describe their values or behavior in hypothetical scenarios. By focusing on unaugmented LLMs, they fall short of

Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure remains insufficiently understood. In this work, we study safety failures from a state-space perspective and show that many multi-turn failures arise from structured contextual state evolution rather than isolated prompt vulnerabilities. We introduce STAR, a st

Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To address these issues, we propose DiFlowDubber, the first video dubbing framework built upon a discrete flow matching backbone with a novel two-stage training strategy. In the first stage, a zero-shot text-to-speech (TTS) system is pre-trained on large-scale corpora, where a deterministic architecture captures linguistic stru

Contemporary AI governance frameworks rely heavily on post hoc oversight, policy guidance, and behavioral alignment techniques, yet these mechanisms become fragile as systems gain autonomy, speed, and operational opacity. This paper presents Aegis, a runtime governance architecture for autonomous AI systems that treats policy and legal constraints as execution conditions rather than advisory principles. Aegis binds each governed agent to a cryptographically sealed Immutable Ethics Policy Layer (

This work proposes a formal abductive explanation framework designed to systematically uncover rationales underlying AI predictions of mental health help-seeking within tech workplace settings. By computing rigorous justifications for model outputs, this approach enables principled selection of models tailored to distinct psychiatric profiles and underpins ethically robust recourse planning. Beyond moving past ad-hoc interpretability, we explicitly examine the influence of sensitive attributes s

Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties. However, their alignment with human object perception remains poorly understood. Here, we introduce a behavioral benchmark in which participants make same/different object judgments for dot pairs on naturalistic scenes, scaling up a classical psychophysics paradigm to over 1000 trials. We test a diverse set of vision models using a

Chain-of-thought (CoT) reasoning has advanced medical visual question answering (VQA), yet most existing CoT rationales are free-form and fail to capture the structured reasoning process clinicians actually follow. This work asks: Can traceable, multi-step reasoning supervision improve reasoning accuracy and the interpretability of Medical VQA? To this end, we introduce Step-CoT, a large-scale medical reasoning dataset with expert-curated, structured multi-step CoT aligned to clinical diagnostic